poca-SoccerTwos / run_logs /timers.json
sd99's picture
First Push
235314c
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.200557231903076,
"min": 2.1654269695281982,
"max": 3.2957420349121094,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 44715.32421875,
"min": 20508.2265625,
"max": 135771.90625,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 53.536842105263155,
"min": 43.669642857142854,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 20344.0,
"min": 13696.0,
"max": 27912.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1504.9396553047186,
"min": 1198.0195788540052,
"max": 1512.235055319367,
"count": 440
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 285938.5345078965,
"min": 2399.5455533704862,
"max": 337016.2787053108,
"count": 440
},
"SoccerTwos.Step.mean": {
"value": 4999934.0,
"min": 9976.0,
"max": 4999934.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999934.0,
"min": 9976.0,
"max": 4999934.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.011560098268091679,
"min": -0.057873934507369995,
"max": 0.24829638004302979,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -2.184858560562134,
"min": -10.938173294067383,
"max": 32.749732971191406,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.012284666299819946,
"min": -0.05925298482179642,
"max": 0.24734929203987122,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.3218019008636475,
"min": -11.198814392089844,
"max": 32.39611053466797,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.16870370333787627,
"min": -0.5555555555555556,
"max": 0.49941159417663794,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -31.884999930858612,
"min": -39.28920006752014,
"max": 63.69419997930527,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.16870370333787627,
"min": -0.5555555555555556,
"max": 0.49941159417663794,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -31.884999930858612,
"min": -39.28920006752014,
"max": 63.69419997930527,
"count": 500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.017001716897357255,
"min": 0.01143802203393231,
"max": 0.0239353696165684,
"count": 236
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.017001716897357255,
"min": 0.01143802203393231,
"max": 0.0239353696165684,
"count": 236
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09065889219443003,
"min": 8.771085750443792e-07,
"max": 0.10946443950136503,
"count": 236
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09065889219443003,
"min": 8.771085750443792e-07,
"max": 0.10946443950136503,
"count": 236
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09303053294618925,
"min": 1.0323220199855618e-06,
"max": 0.11251178806026776,
"count": 236
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09303053294618925,
"min": 1.0323220199855618e-06,
"max": 0.11251178806026776,
"count": 236
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 236
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 236
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 236
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 236
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 236
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 236
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675593386",
"python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\easys\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training_executables/SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.13.1+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1675621136"
},
"total": 27749.976110199997,
"count": 1,
"self": 0.5080020999994304,
"children": {
"run_training.setup": {
"total": 0.13246309999999983,
"count": 1,
"self": 0.13246309999999983
},
"TrainerController.start_learning": {
"total": 27749.335645,
"count": 1,
"self": 14.134381000494614,
"children": {
"TrainerController._reset_env": {
"total": 7.018257799999585,
"count": 25,
"self": 7.018257799999585
},
"TrainerController.advance": {
"total": 27727.979558899508,
"count": 331898,
"self": 15.267474698543083,
"children": {
"env_step": {
"total": 11476.352125499963,
"count": 331898,
"self": 9068.976639699527,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2398.0581362001535,
"count": 331898,
"self": 84.52094710010033,
"children": {
"TorchPolicy.evaluate": {
"total": 2313.537189100053,
"count": 639160,
"self": 2313.537189100053
}
}
},
"workers": {
"total": 9.317349600282007,
"count": 331898,
"self": 0.0,
"children": {
"worker_root": {
"total": 27723.965226400378,
"count": 331898,
"is_parallel": true,
"self": 20341.273018700464,
"children": {
"steps_from_proto": {
"total": 0.07796279999779898,
"count": 50,
"is_parallel": true,
"self": 0.015160600019098247,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.06280219997870073,
"count": 200,
"is_parallel": true,
"self": 0.06280219997870073
}
}
},
"UnityEnvironment.step": {
"total": 7382.614244899914,
"count": 331898,
"is_parallel": true,
"self": 384.3647253007748,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 292.1843568999095,
"count": 331898,
"is_parallel": true,
"self": 292.1843568999095
},
"communicator.exchange": {
"total": 5451.734033799561,
"count": 331898,
"is_parallel": true,
"self": 5451.734033799561
},
"steps_from_proto": {
"total": 1254.3311288996688,
"count": 663796,
"is_parallel": true,
"self": 243.5456137008939,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1010.7855151987749,
"count": 2655184,
"is_parallel": true,
"self": 1010.7855151987749
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 16236.359958701001,
"count": 331898,
"self": 91.37951629971576,
"children": {
"process_trajectory": {
"total": 2056.410086801281,
"count": 331898,
"self": 2054.006195701282,
"children": {
"RLTrainer._checkpoint": {
"total": 2.403891099998873,
"count": 10,
"self": 2.403891099998873
}
}
},
"_update_policy": {
"total": 14088.570355600004,
"count": 236,
"self": 1091.0782428999973,
"children": {
"TorchPOCAOptimizer.update": {
"total": 12997.492112700007,
"count": 7083,
"self": 12997.492112700007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2999989849049598e-06,
"count": 1,
"self": 1.2999989849049598e-06
},
"TrainerController._save_models": {
"total": 0.2034459999995306,
"count": 1,
"self": 0.015442600000824314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1880033999987063,
"count": 1,
"self": 0.1880033999987063
}
}
}
}
}
}
}